Data Analytics in Julia
By Rongxin Ouyang, PhD student in Computational Communication, NUS
(Generated by GPT-4o)
Scope
This short book provides a practical guide for data analysis in social science using Julia. It replicates common analytical steps in the field.
Because of its speed.
Outline
β Why do we need Julia
β How to install Julia
β How to install Julia as a Jupyter kernal for notebooks
β The basics of operations, data structures, packages, methods, and define functions
β Chapter 2. Data Loading and Selection
β Load a dataframe from a local file, an online link, and a common datasets; or create it from scratch
β Select by rows, columns, and conditions.
β Chapter 3. Transformation and calculation
β Split and combine
β Grouping
β Sorting
β Transforming between long / wide tables
β Find / fill / drop missing values
β Chapter 4. Pipeline and Useful Packages
β Data pipeline
β Manipulate strings
β Network
β Chapter 5.1 Models and Tests
β Common parametric tests (t-tests and ANOVA)
β Regression (multi-variate regression and fixed effects models)
β Path Analysis
β Mediation
β Moderation
β Conditional Path Analysis
β Chapter 5.2 Models and Tests (continued)
π§ / β Counterfactual Framework
π§ / β Instrumental Variables
π§ / β Regression Discontinuity Design
π§ / β Difference-in-Difference
π§ / β Synthetic Control
π§ / β Synthetic Difference-in-Difference
β Chapter 6. Visualization (ggplot2-like)
β Scatterplot, barplot, lineplot, and histogram
β Styles and themes
β Multiple-plots in facets
β Chapter 7. Using R and Python in Julia
β Using R functions and R code blocks in Julia
β Using Python functions and Python code blocks in Julia
β Chapter 8. Performance Optimization
β Tips for increasing the speed
β Profiling tool and visualization
β Appendix. Codes for plotting
β All codes used for plotting
License
This work is licensed under aCreative Commons Attribution-NonCommercial 4.0 International License.
Last updated
Was this helpful?